[
https://issues.apache.org/jira/browse/FLINK-22001?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Robert Metzger reassigned FLINK-22001:
--------------------------------------
Assignee: Robert Metzger
> Exceptions from JobMaster initialization are not forwarded to the user
> ----------------------------------------------------------------------
>
> Key: FLINK-22001
> URL: https://issues.apache.org/jira/browse/FLINK-22001
> Project: Flink
> Issue Type: Bug
> Components: Runtime / Coordination
> Affects Versions: 1.13.0
> Reporter: Robert Metzger
> Assignee: Robert Metzger
> Priority: Blocker
> Fix For: 1.13.0
>
>
> Steps to reproduce:
> Set up a streaming job with an invalid parallelism configuration, for example:
> {code}
> .setParallelism(15).setMaxParallelism(1);
> {code}
> This should report the following exception to the user:
> {code}
> Caused by: org.apache.flink.runtime.JobException: Vertex
> Window(GlobalWindows(), DeltaTrigger, TimeEvictor, ComparableAggregator,
> PassThroughWindowFunction)'s parallelism (15) is higher than the max
> parallelism (1). Please lower the parallelism or increase the max parallelism.
> at
> org.apache.flink.runtime.executiongraph.ExecutionJobVertex.<init>(ExecutionJobVertex.java:160)
> at
> org.apache.flink.runtime.executiongraph.DefaultExecutionGraph.attachJobGraph(DefaultExecutionGraph.java:781)
> at
> org.apache.flink.runtime.executiongraph.DefaultExecutionGraphBuilder.buildGraph(DefaultExecutionGraphBuilder.java:193)
> at
> org.apache.flink.runtime.scheduler.DefaultExecutionGraphFactory.createAndRestoreExecutionGraph(DefaultExecutionGraphFactory.java:106)
> at
> org.apache.flink.runtime.scheduler.SchedulerBase.createAndRestoreExecutionGraph(SchedulerBase.java:252)
> at
> org.apache.flink.runtime.scheduler.SchedulerBase.<init>(SchedulerBase.java:185)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.<init>(DefaultScheduler.java:119)
> at
> org.apache.flink.runtime.scheduler.DefaultSchedulerFactory.createInstance(DefaultSchedulerFactory.java:132)
> at
> org.apache.flink.runtime.jobmaster.DefaultSlotPoolServiceSchedulerFactory.createScheduler(DefaultSlotPoolServiceSchedulerFactory.java:110)
> at
> org.apache.flink.runtime.jobmaster.JobMaster.createScheduler(JobMaster.java:340)
> at
> org.apache.flink.runtime.jobmaster.JobMaster.<init>(JobMaster.java:317)
> at
> org.apache.flink.runtime.jobmaster.factories.DefaultJobMasterServiceFactory.createJobMasterService(DefaultJobMasterServiceFactory.java:94)
> at
> org.apache.flink.runtime.jobmaster.factories.DefaultJobMasterServiceFactory.createJobMasterService(DefaultJobMasterServiceFactory.java:39)
> at
> org.apache.flink.runtime.jobmaster.JobManagerRunnerImpl.startJobMasterServiceSafely(JobManagerRunnerImpl.java:363)
> ... 13 more
> {code}
> However, what the user sees is
> {code}
> 2021-03-28 20:32:33,935 INFO
> org.apache.flink.runtime.dispatcher.StandaloneDispatcher [] - Job
> 419f60eac551619fc1081c670ced3649 reached globally terminal state FAILED.
> ...
> 2021-03-28 20:32:33,974 INFO
> org.apache.flink.runtime.dispatcher.StandaloneDispatcher [] - Stopped
> dispatcher akka://flink/user/rpc/dispatcher_2.
> 2021-03-28 20:32:33,977 INFO
> org.apache.flink.runtime.rpc.akka.AkkaRpcService [] - Stopping
> Akka RPC service.
> Exception in thread "main" org.apache.flink.util.FlinkException: Failed to
> execute job 'CarTopSpeedWindowingExample'.
> at
> org.apache.flink.streaming.api.environment.StreamExecutionEnvironment.executeAsync(StreamExecutionEnvironment.java:1975)
> at
> org.apache.flink.streaming.api.environment.StreamExecutionEnvironment.execute(StreamExecutionEnvironment.java:1853)
> at
> org.apache.flink.streaming.api.environment.LocalStreamEnvironment.execute(LocalStreamEnvironment.java:69)
> at
> org.apache.flink.streaming.api.environment.StreamExecutionEnvironment.execute(StreamExecutionEnvironment.java:1839)
> at
> org.apache.flink.streaming.examples.windowing.TopSpeedWindowing.main(TopSpeedWindowing.java:101)
> Caused by: java.lang.RuntimeException: Error while waiting for job to be
> initialized
> at
> org.apache.flink.client.ClientUtils.waitUntilJobInitializationFinished(ClientUtils.java:160)
> at
> org.apache.flink.client.program.PerJobMiniClusterFactory.lambda$submitJob$2(PerJobMiniClusterFactory.java:83)
> at
> org.apache.flink.util.function.FunctionUtils.lambda$uncheckedFunction$2(FunctionUtils.java:73)
> at
> java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616)
> at
> java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591)
> at
> java.util.concurrent.CompletableFuture$Completion.exec(CompletableFuture.java:457)
> at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
> at
> java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
> at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
> at
> java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:157)
> Caused by: java.util.concurrent.ExecutionException:
> org.apache.flink.util.FlinkException: JobMaster has been shut down.
> at
> java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:357)
> at
> java.util.concurrent.CompletableFuture.get(CompletableFuture.java:1908)
> at
> org.apache.flink.client.program.PerJobMiniClusterFactory.lambda$null$0(PerJobMiniClusterFactory.java:89)
> at
> org.apache.flink.client.ClientUtils.waitUntilJobInitializationFinished(ClientUtils.java:144)
> ... 9 more
> Caused by: org.apache.flink.util.FlinkException: JobMaster has been shut down.
> at
> org.apache.flink.runtime.jobmaster.JobManagerRunnerImpl.closeAsync(JobManagerRunnerImpl.java:197)
> at
> java.util.concurrent.CompletableFuture.uniComposeStage(CompletableFuture.java:995)
> at
> java.util.concurrent.CompletableFuture.thenCompose(CompletableFuture.java:2137)
> at
> org.apache.flink.runtime.dispatcher.DispatcherJob.lambda$closeAsync$8(DispatcherJob.java:273)
> at
> java.util.concurrent.CompletableFuture.uniHandle(CompletableFuture.java:836)
> at
> java.util.concurrent.CompletableFuture.uniHandleStage(CompletableFuture.java:848)
> at
> java.util.concurrent.CompletableFuture.handle(CompletableFuture.java:2168)
> at
> org.apache.flink.runtime.dispatcher.DispatcherJob.closeAsync(DispatcherJob.java:268)
> at
> org.apache.flink.runtime.dispatcher.Dispatcher.removeJob(Dispatcher.java:754)
> at
> org.apache.flink.runtime.dispatcher.Dispatcher.lambda$runJob$4(Dispatcher.java:432)
> at
> java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616)
> at
> java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591)
> at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
> at
> java.util.concurrent.CompletableFuture.postFire(CompletableFuture.java:575)
> at
> java.util.concurrent.CompletableFuture$UniHandle.tryFire(CompletableFuture.java:814)
> at
> java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:456)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:440)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:208)
> at
> org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:77)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:158)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
> at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123)
> at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> at akka.actor.Actor$class.aroundReceive(Actor.scala:517)
> at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
> at akka.actor.ActorCell.invoke(ActorCell.scala:561)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
> at akka.dispatch.Mailbox.run(Mailbox.scala:225)
> at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
> at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> at
> akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> at
> akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> 2021-03-28 20:32:34,011 INFO
> org.apache.flink.runtime.rpc.akka.AkkaRpcService [] - Stopping
> Akka RPC service.
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)